lamindb

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and processes untrusted public content — e.g., HTTP/HTTPS artifacts and remote files ("artifact = ln.Artifact('https://example.com/data.csv')" in references/integrations.md), HuggingFace datasets, REST API fetching examples, and public ontology lookup/import_source (references/ontologies.md) — and the agent is expected to read/standardize/validate that content as part of curation workflows, so it can be a vector for indirect prompt injection.